Systems and methods are described for selecting content item identifiers for display. The system may identify a set of content items that are likely to be requested in the future based on a history of content item requests. The system then selects a first plurality of content categories using a category selection neural net and selects a first set of recommended content items for the first plurality of content categories. The system increases a reward score for the first plurality of content categories based on receiving a request for a content item that is included in the first set of recommended content items. The system also decreases the reward score for the first plurality of content categories based on determining that the requested content item is included in the set of content items that are likely to be requested in the future. The neural net is trained based on the reward score of the first plurality of content categories to reinforce reward score maximization. The trained neural net is the used to select content items for display.
Legal claims defining the scope of protection, as filed with the USPTO.
4. The method of claim 3, wherein the content item likely to be requested by the user in the future is an episode of a TV series previously consumed by the user.
5. The method of claim 1, wherein the first and second category are determined to be related based on the list of relatedness if the first and second categories are horror and suspense.
6. The method of claim 1, further comprising tracking reward score for the first category separate from reward scores for other categories.
7. The method of claim 1, further comprising generating an explorative display that includes identifiers of the list of content items related to the first category for selection.
8. The method of claim 7, wherein the explorative display includes identifiers of selected content items in a horizontally arranged format.
9. The method of claim 1, wherein decreasing the reward score is indicative of the second category being non-homogenous to the first category.
10. The method of claim 1, wherein the first and second category are determined to be unrelated based on the list of relatedness if the first and second categories are romance and education.
14. The system of claim 13, wherein the content item that is likely to be requested by the user in the future is an episode of a TV series previously consumed by the user.
15. The system of claim 11, wherein the first and second category are listed as related in the list of relatedness if the first and second categories are horror and suspense.
16. The system of claim 11, further comprising, the control circuitry configured to track reward score for the first category separate from reward scores for other categories.
17. The system of claim 11, further comprising, the control circuitry configured to generate an explorative display that includes identifiers of the list of content items related to the first category for selection.
18. The system of claim 17, wherein the explorative display includes identifiers of selected content items in a horizontally arranged format.
19. The system of claim 11, wherein decreasing the reward score is indicative of the second category being non-homogenous to the first category.
20. The system of claim 11, wherein the first and second category are determined to be unrelated based on the list of relatedness if the first and second categories are romance and education.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
June 1, 2023
November 19, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.